Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Formal/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    镁
    -0.07
    센터
    -0.07
     CARE
    -0.07
    serialization
    -0.07
    :any
    -0.07
     freel
    -0.07
    direct
    -0.07
    ntl
    -0.06
    缴纳
    -0.06
     Superior
    -0.06
    POSITIVE LOGITS
    .IsNullOrWhiteSpace
    0.08
    ıyord
    0.07
    Adventure
    0.06
    "↵↵↵↵
    0.06
     QDir
    0.06
     hu
    0.06
    );
↵
↵
↵
    0.06
     mockery
    0.06
     lesbische
    0.06
     wybra
    0.06
    Act Density 0.380%

    No Known Activations